| More

Application of Artificial Neural Networks on improving predictions of nuclear radii

Views: 61 Downloads: 30
V. Skarlis, E. Bratsolis, E. Charou, T. J. Mertzimekis
V. Skarlis, E. Bratsolis, E. Charou, T. J. Mertzimekis

Abstract


Artificial Neural Networks (ANN) are mathematical computing paradigms imitating the operations of biological neural systems. Their nonlinear nature and ability to learn from the environment make them highly suited to solve real-world problems from those that are still under development. In the field of Physics there are many problems which cannot be adequately solved with the physics–based methods and the use of ANN may yield better results. In the present work ANNs have been tested in predicting nuclear radii considering as input the atomic and mass numbers, exclusively. The performance of different supervised ANNs is evaluated. The dataset used for the training and testing was based on evaluated data of nuclear radii available in IAEA tables.

Keywords


Artificial Neural Networks; nuclear charge radii

Full Text:

PDF


DOI: http://dx.doi.org/10.12681/hnps.1796

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 V. Skarlis, E. Bratsolis, E. Charou, T. J. Mertzimekis

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.